Performance Prediction of Green Supply Chain Using Bayesian Belief Network: Case Study of a Textile Industry

In managing a supply chain, the green approach has become pivotal for the sake of environmental, economic, and social sustainability. In this paper, we consider the environmental performance prediction in managing sourcing of a textile industry supply chain. Specifically, this research focuses on the dying sector of an emerging economy. We identify eleven green supply chain performance indicators and four performance measures and perform both qualitative and quantitative analyses. The performance is predicted using a probabilistic model based on a Bayesian belief network (BBN). The robustness of the findings is validated through a sensitivity analysis. The outcomes suggest that ‘total suspended solids’ (TSS) and ‘volatile organic compounds’ (VOC) are the most important indicators for the case company in this study with the highest entropy reduction. Also, ‘air emission’ was found to be the most impactful performance measure for entropy reduction. This research work will help improve the decision-making capability of the managers and practitioners considering the total environmental performance of the green supply chain. The improved decision-making will also improve overall organizational performance of a green supply chain.

Keywords:

Green supply chain , Sustainability , Bayesian , Performance Prediction , textile industry